Qing Lei's repositories
async-zmq
Async version for ZeroMQ bindings
bb8-rusqlite
A bb8 connection manager for rusqlite
cacache-rs
A high-performance, concurrent, content-addressable disk cache, with support for both sync and async APIs. 💩💵 but for your 🦀
ChatTTS
ChatTTS is a generative speech model for daily dialogue.
CogVLM2
GPT4V-level open-source multi-modal model based on Llama3-8B
Descent3
Descent 3 by Outrage Entertainment
EasyCV
An all-in-one toolkit for computer vision
FaceBagNet
FaceBagNet - Patch-based Methods for Multi-modal Face Anti-spoofing (FAS)
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
game-garden
掘金游戏后花园,丰富想象,与掘友一起共建游戏社区。
grok-1
Grok open release
http-cache
A caching middleware that follows HTTP caching rules
http-client
Types and traits for http clients
insightface
State-of-the-art 2D and 3D Face Analysis Project
is3rlab.github.io
Intelligent Social Systems and Swarm Robotics Lab (IS3R)
llama-recipes
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.
llama3
The official Meta Llama 3 GitHub site
r2d2-sqlite
r2d2 connection pool for sqlite
redislock
Distributed locks with Redis, implemented in Rust
rocketmq-clients
RocketMQ Clients - Collection of Client Bindings for Apache RocketMQ
SeaLLMs
SeaLLMs - Large Language Models for Southeast Asia
SenseVoice
Multilingual Voice Understanding Model
surf
Fast and friendly HTTP client framework for async Rust
tide-compress
Outgoing compression middleware for the Tide web framework.
weighted-rs
A Rust library for weighted balancing algorithm
whisper
Robust Speech Recognition via Large-Scale Weak Supervision
word2vec-rs
pure rust implemention of word2vec
ZLUDA
CUDA on ??? GPUs